Instructions to use rovdetection/code-1b-expert-assistant with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rovdetection/code-1b-expert-assistant with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("rovdetection/code-1b-expert-assistant", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Training in progress, step 1000
Browse files- README.md +1 -1
- adapter_config.json +6 -8
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: transformers
|
|
| 4 |
model_name: code-1b-expert-assistant
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
- trl
|
| 8 |
- sft
|
|
|
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
|
|
|
| 4 |
model_name: code-1b-expert-assistant
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
|
|
|
| 7 |
- sft
|
| 8 |
+
- trl
|
| 9 |
licence: license
|
| 10 |
---
|
| 11 |
|
adapter_config.json
CHANGED
|
@@ -19,29 +19,27 @@
|
|
| 19 |
"lora_alpha": 256,
|
| 20 |
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.05,
|
| 22 |
-
"lora_ga_config": null,
|
| 23 |
"megatron_config": null,
|
| 24 |
"megatron_core": "megatron.core",
|
| 25 |
"modules_to_save": null,
|
| 26 |
"peft_type": "LORA",
|
| 27 |
-
"peft_version": "0.
|
| 28 |
"qalora_group_size": 16,
|
| 29 |
"r": 128,
|
| 30 |
"rank_pattern": {},
|
| 31 |
"revision": null,
|
| 32 |
"target_modules": [
|
|
|
|
|
|
|
| 33 |
"v_proj",
|
| 34 |
-
"
|
| 35 |
"up_proj",
|
| 36 |
-
"
|
| 37 |
-
"k_proj"
|
| 38 |
-
"q_proj",
|
| 39 |
-
"o_proj"
|
| 40 |
],
|
| 41 |
"target_parameters": null,
|
| 42 |
"task_type": "CAUSAL_LM",
|
| 43 |
"trainable_token_indices": null,
|
| 44 |
-
"use_bdlora": null,
|
| 45 |
"use_dora": false,
|
| 46 |
"use_qalora": false,
|
| 47 |
"use_rslora": false
|
|
|
|
| 19 |
"lora_alpha": 256,
|
| 20 |
"lora_bias": false,
|
| 21 |
"lora_dropout": 0.05,
|
|
|
|
| 22 |
"megatron_config": null,
|
| 23 |
"megatron_core": "megatron.core",
|
| 24 |
"modules_to_save": null,
|
| 25 |
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.1",
|
| 27 |
"qalora_group_size": 16,
|
| 28 |
"r": 128,
|
| 29 |
"rank_pattern": {},
|
| 30 |
"revision": null,
|
| 31 |
"target_modules": [
|
| 32 |
+
"q_proj",
|
| 33 |
+
"down_proj",
|
| 34 |
"v_proj",
|
| 35 |
+
"o_proj",
|
| 36 |
"up_proj",
|
| 37 |
+
"gate_proj",
|
| 38 |
+
"k_proj"
|
|
|
|
|
|
|
| 39 |
],
|
| 40 |
"target_parameters": null,
|
| 41 |
"task_type": "CAUSAL_LM",
|
| 42 |
"trainable_token_indices": null,
|
|
|
|
| 43 |
"use_dora": false,
|
| 44 |
"use_qalora": false,
|
| 45 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 363365712
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ece9918ba6ae7ff5c6354d8843a6ff5e36f4fd5dcd0c2fc4f171e781fa6c7b95
|
| 3 |
size 363365712
|